{"id":"https://openalex.org/W4391306885","doi":"https://doi.org/10.1109/vcip59821.2023.10402739","title":"SpeechSyncNet: Speech to Talking Landmark via the fusion of prior frame landmark and the audio","display_name":"SpeechSyncNet: Speech to Talking Landmark via the fusion of prior frame landmark and the audio","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4391306885","doi":"https://doi.org/10.1109/vcip59821.2023.10402739"},"language":"en","primary_location":{"id":"doi:10.1109/vcip59821.2023.10402739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip59821.2023.10402739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005429804","display_name":"Xuan-Nam Cao","orcid":"https://orcid.org/0000-0002-3614-7982"},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]},{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Xuan-Nam Cao","raw_affiliation_strings":["University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam","Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam","Vietnam National University, Ho Chi Minh City, Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I23582244"]},{"raw_affiliation_string":"Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I23582244"]},{"raw_affiliation_string":"Vietnam National University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025256654","display_name":"Quoc-Huy Trinh","orcid":"https://orcid.org/0000-0002-7205-3211"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]},{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Quoc-Huy Trinh","raw_affiliation_strings":["University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam","Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam","Vietnam National University, Ho Chi Minh City, Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I23582244"]},{"raw_affiliation_string":"Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I23582244"]},{"raw_affiliation_string":"Vietnam National University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016855893","display_name":"Van-Son Ho","orcid":"https://orcid.org/0000-0002-8389-2176"},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]},{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Van-Son Ho","raw_affiliation_strings":["University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam","Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam","Vietnam National University, Ho Chi Minh City, Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I23582244"]},{"raw_affiliation_string":"Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I23582244"]},{"raw_affiliation_string":"Vietnam National University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053495766","display_name":"Minh\u2013Triet Tran","orcid":"https://orcid.org/0000-0003-3046-3041"},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]},{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Minh-Triet Tran","raw_affiliation_strings":["University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam","Vietnam National University, Ho Chi Minh City, Vietnam","Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I23582244"]},{"raw_affiliation_string":"Vietnam National University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I123565023"]},{"raw_affiliation_string":"Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I23582244"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005429804"],"corresponding_institution_ids":["https://openalex.org/I123565023","https://openalex.org/I23582244"],"apc_list":null,"apc_paid":null,"fwci":0.4066,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60900044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9751999974250793,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.921999990940094,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.9768298268318176},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.693486750125885},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6163383722305298},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5685332417488098},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4685196578502655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38881585001945496},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18998104333877563},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.16253170371055603}],"concepts":[{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.9768298268318176},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.693486750125885},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6163383722305298},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5685332417488098},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4685196578502655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38881585001945496},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18998104333877563},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.16253170371055603},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip59821.2023.10402739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip59821.2023.10402739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W2064675550","https://openalex.org/W2526050071","https://openalex.org/W2752782242","https://openalex.org/W2795230330","https://openalex.org/W2804619907","https://openalex.org/W2900292050","https://openalex.org/W2944294033","https://openalex.org/W2955821113","https://openalex.org/W2963081548","https://openalex.org/W2972612102","https://openalex.org/W2979894294","https://openalex.org/W2981263323","https://openalex.org/W2981767644","https://openalex.org/W3019952993","https://openalex.org/W3023706973","https://openalex.org/W3099284785","https://openalex.org/W3100777112","https://openalex.org/W3105763085","https://openalex.org/W3109114891","https://openalex.org/W3174763799","https://openalex.org/W3186700381","https://openalex.org/W4210657261","https://openalex.org/W4281779270","https://openalex.org/W4288327876","https://openalex.org/W4375868855","https://openalex.org/W4385245566","https://openalex.org/W4386066256","https://openalex.org/W6739901393","https://openalex.org/W6764045775","https://openalex.org/W6765224460","https://openalex.org/W6776963518"],"related_works":["https://openalex.org/W2056853153","https://openalex.org/W2057559274","https://openalex.org/W2005087563","https://openalex.org/W2378111931","https://openalex.org/W4243161226","https://openalex.org/W2950647290","https://openalex.org/W2620829895","https://openalex.org/W2356918560","https://openalex.org/W1968481813","https://openalex.org/W2392886708"],"abstract_inverted_index":{"Accurately":[0],"generating":[1],"talking":[2,11,48,136],"landmarks":[3],"from":[4,25,50,72,104],"audio":[5,26,95],"is":[6,15],"critical":[7],"for":[8],"creating":[9],"authentic":[10],"head":[12],"animations.":[13],"This":[14],"a":[16,82,86],"significant":[17],"issue":[18],"in":[19,31,62],"the":[20,43,47,67,73,89,94,99,112,115,133],"field":[21],"of":[22,69,88,101,114,135],"landmark":[23,49,63,91,116,138],"generation":[24,64],"and":[27,38,60,93,129],"has":[28],"potential":[29],"applications":[30],"areas":[32],"such":[33,57],"as":[34,58],"virtual":[35],"assistants,":[36],"education,":[37],"entertainment.":[39],"Previous":[40],"methods":[41,54,128],"evaluate":[42],"effectiveness":[44],"to":[45,66,97,110,125,131],"generate":[46],"audio,":[51,105],"however,":[52],"these":[53],"have":[55],"limitations":[56],"bias":[59],"inconsistencies":[61],"due":[65],"lack":[68,100],"visual":[70,102],"information":[71,92,103],"previous":[74],"frames.":[75],"In":[76],"this":[77,107],"research,":[78],"we":[79],"propose":[80],"SpeechSyncNet,":[81],"baseline":[83],"that":[84],"integrates":[85],"fusion":[87],"prior":[90],"feature":[96],"provide":[98],"also":[106],"method":[108,120],"aims":[109],"improve":[111,132],"consistency":[113],"motion.":[117],"Our":[118],"proposed":[119],"yields":[121],"competitive":[122],"results":[123],"compared":[124],"existing":[126],"state-of-the-art":[127],"helps":[130],"quality":[134],"face":[137],"generation.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
